P

mcp_media_generator

...
Created 1/25/2025bydvejsada

Categories

amazon-bedrockimage-generationlibrechatmcpvideo-generation

Language:

Python

Stars:

2

Forks:

0

What is it?

A Model Context Protocol Server running over SSE

What it offers?

Tools to create images using Amazon Nova Canvas model and videos using Amazon Nova Reel model.

What do I need?

  • Amazon Bedrock account with access to Amazon Nova Canvas and Amazon Nova Reel models.
  • Amazon S3 bucket to store the video
  • MCP Client, such is Claude Desktop or LibreChat

How to run this?

Using Docker with precompiled image as per docker-compose.yml. App is listening on port 8961.

How to add to LibreChat

In your librechat.yaml file, add the following section:

mcpServers:
  media-creator:
    type: sse # type can optionally be omitted
    url: URL of your docker container # e.g. http://localhost:8961/sse

How to use in LibreChat

After the server is added to LibreChat as per above, restart LibreChat to connect to MCP server and discover tools. Then, create an agent and add the respective tools to agent.

When the agent is created, you may ask the agent to create image or video which should invoke the provided tools.

Last updated: 2/12/2025

Publisher info

dvejsada's avatar

george

Lawyer with the interest in programming.

Prague
7
followers
3
following
13
repos

More MCP servers built with Python

composer-trade-mcp

Create, backtest, and execute trades directly in one chat box. The Composer MCP Server gives LLMs the power to backtest investment ideas and execute automated trading strategies. Trade across stocks, ETFs, and crypto directly in Claude.

By https://github.com/ronnyli
slidespeak-mcp

An MCP to generate presentations with AI. Create and edit PowerPoint presentations with AI.

By https://github.com/SlideSpeak
PaddleOCR

The PaddleOCR MCP server brings enterprise-grade OCR and document parsing capabilities to AI applications. Built on PaddleOCR — a proven solution with 50,000+ GitHub stars, deeply integrated by leading projects like MinerU, RAGFlow, and OmniParser— with targeted optimizations based on the MCP concept.

By PaddlePaddle